彩色濾光膜(color filter, CF)為CMOS（互補式金屬氧化物半導體，complementary metal-oxide-semiconductor）影像感測器（CMOS image sensor, CIS）的關鍵組件，對CMOS影像感測器製造商而言，彩色濾光膜製程良率是品質維護、提高收益的重要因素。自動光學檢測（automated optical inspection, AOI）為檢測晶圓之表面缺陷的關鍵設備，且已廣泛應用於半導體領域，AOI能提供晶圓的高解析度圖像，在取得影像資訊上具重要影響性。AOI雖然能檢測出缺陷影像進而降低人力成本，但卻無法有效識別出缺陷之類型，以至於無法協助專家追溯缺陷原因。本研究發展一套結合相似度匹配（similarity matching）功能之彩色濾光膜缺陷影像分類模式，除了整合影像分析與資料挖礦技術進行缺陷分類之外，相似度匹配進一步降低影像預測誤判率（false alarm），進而有效達到製造商的實際目標。本研究以新竹科學園區某CMOS影像感測器製造商為例，收集彩色濾光膜製程缺陷影像進行分析與實證，所提出方法的有效性和結果也證明了其實用價值。

For CMOS image sensor (CIS) manufacturing, defect reduction is a key taskforce for quality assurance and yield enhancement. Indeed, automatic optical inspection (AOI) is the critical equipment for defect inspection. Although AOI can capture possible defect images with high throughput and low manual labor, it cannot identify defect types for troubleshooting purpose. In particular, the advanced AOI equipment can provide a high resolution defect image of a whole wafer for overall judgments. This study aims to develop a hybrid data mining approach for defect classification for whole wafer images based on the result of classifier. The proposed approach consists of two stages similarity matching to rearrange the order of features from different images of CMOS. This concept could not only reduce the false alarm rate but enhance the correct rate. An empirical study was conducted with a leading CIS manufacturing company in Taiwan to estimate the validity and the results also demonstrated the practical value of the proposed approach.

摘要 I
Abstract II
圖目錄 V
表目錄 VI
一、緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 論文架構 2
二、理論基礎 4
2.1 彩色濾光膜製程與缺陷類型 4
2.2 缺陷偵測 7
2.3 資料挖礦技術於缺陷分類之應用 8
2.4 相似度匹配 10
三、研究架構 11
3.1 問題定義 11
3.2 資料準備 14
3.2.1 邊緣偵測 14
3.3.2 特徵值擷取 15
3.3 SVM二元過濾器 17
3.4 決策樹分類與相似度匹配 19
3.5 結果評估 22
四、實證研究 24
4.1 實驗設計 24
4.2 資料準備討論 26
4.2.1 偵測結果 26
4.2.2 特徵值萃取結果 27
4.3 SVM二元過濾器結果 28
4.4 分類與相似度匹配結果 29
4.5 綜合討論 32
五、結論與未來研究 34
參考文獻 35

簡禎富、許嘉裕，資料挖礦與大數據分析，前程文化，新北（2014）。
Canny, J., “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), 679-698 (1986).
Chang, C.-C. and C.-J. Lin, “LIBSVM: a library for support vector machines,” ACM Transactions on Intelligent Systems and Technology, 2(3), 27:1-27:27 (2011).
Chen, Y.-J., T.-H. Lin, K.-H. Chang, and C.-F. Chien, “Feature extraction for defect classification and yield enhancement in color filter and micro-lens manufacturing: An empirical study,” Journal of Industrial and Production Engineering, 30(8), 510-517 (2013).
Chien, C.-F. and C.-Y. Hsu, “A novel method for determining machine subgroups and backups with an empirical study for semiconductor manufacturing,” Journal of Intelligent Manufacturing, 17(4), 429-439 (2006).
Chien, C.-F., S.-C. Hsu, and Y.-J. Chen, “A system for online detection and classification of wafer bin map defect patterns for manufacturing intelligence,” International Journal of Production Research, 51(8), 2324-2338 (2013).
Chien, C.-F., Y.-J. Chen, and C.-Y. Hsu, “A novel approach to hedge and compensate the critical dimension variation of the developed-and-etched circuit patterns for yield enhancement in semiconductor manufacturing,” Computers & Operations Research, 53, 309-318 (2015).
Choi, G., S.-H. Kim, Chunghun Ha, and S. J. Bae, “Multi-step ART1 algorithm for recognition of defect patterns on semiconductor wafers,” International Journal of Production Research, 50(12), 3274-3287 (2012).
Cortes, C. and V. Vapnik, “Support-vector networks,” Machine Learning, 20(3), 273-297 (1995).
Kuo, C.-F., C.-T. M. Hsu, C.-H. Fang, S.-M. Chao, and Y.-D. Lin, “Automatic defect inspection system of color filters using Taguchi-based neural network,” International Journal of Production Research, 51(5), 1464-1476 (2013).
Li, W.-C. and D.-M. Tsai, “Wavelet-based defect detection in solar wafer images with inhomogeneous texture,” Pattern Recognition, 45(2), 742-756 (2012).
Liao, C.-S., T.-J. Hsieh, Y.-S. Huang, and C.-F. Chien, “Similarity searching for defective wafer bin maps in semiconductor manufacturing,” IEEE Transactions on Automation Science and Engineering, 11(3), 953-960 (2014).
Nigam, A. and P. Gupta “Comparing human faces using edge weighted dissimilarity measure,” Control Automation Robotics & Vision, 2010 11th International Conference on. IEEE, 1831-1836 (2010).
Huang, S.-H. and Y.-C. Pan, “Automated visual inspection in the semiconductor industry: A survey,” Computers in Industry, 66, 1-10 (2015).
Otsu, N., “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man and Cybernetics, 9(1), 62-66 (1979).
Tsai, D.-M. and J.-Y. Luo, “Mean shift-based defect detection in multi-crystalline solar wafer surfaces,” IEEE Transactions on Industrial Informatics, 7(1), 125-135 (2011).
Tsai, D.-M., S.-C. Wu, and W.-Y. Chiu, “Defect detection in solar modules using ICA basis images,” IEEE Transactions on Industrial Informatics, 9(1), 122-131 (2013).
Tsai, D.-M., S.-C. Wu, and W.-C. Li, “Defect detection of solar cells in electroluminescence images using Fourier image reconstruction image reconstruction,” Solar Energy Materials & Solar Cells, 99, 250-262 (2012).
Tseng, D.-C., I.-L. Chung, P.-L. Tsai, and C-.M. Chou, “Defect classification for LCD color filters using neural-network decision tree classifier,” International Journal of Innovative Computing, Information and Control, 7(7A), 3695-3707 (2011).
Zhu, Z., M. Tang, and H. Lu, “A new robust circular Gabor based object matching by using weighted Hausdorff distance,” Pattern Recognition Letters, 25(4), 515-523 (2004).